INDEX

Explanations

metadata and information related to archival content

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CEO

-0.15

erset

-0.14

Ð°ÑĤÐ°ÑĢ

-0.14

 veniam

-0.13

CVS

-0.13

Ø§Ø²ÙĦ

-0.13

lbrace

-0.13

MethodName

-0.13

ICES

-0.13

raki

-0.13

POSITIVE LOGITS

LC

0.29

 Library

0.27

 Prints

0.26

DLC

0.24

LC

0.24

 Rights

0.23

hdl

0.23

Library

0.23

Rights

0.23

 rights

0.22

Activations Density 0.012%

metadata and information related to archival content

No Comments

No Known Activations